pickup-session

Resume from a handoff and live repository evidence.

SKILL.md

GitHub
<!-- Generated by mstack from Misbah's Build Like This workflow. Regenerate instead of editing. -->

pickup-session

Run the session-pickup skill. Verify claimed progress against artifacts and continue only the remaining frontier.

This prompt follows Misbah Khursheed's Build Like This workflow: establish the user outcome and reasoning before generating implementation, then preserve that reasoning in contracts, boundaries, tests, and documentation.

Project identity and sources of truth

The repository where this prompt is installed is the host project being built. Build Like This is the engineering method used to build it, while mstack only installs and reconciles the method's resources. Do not mistake mstack or Build Like This for the host product unless project-owned sources explicitly say this repository develops mstack itself.

Project-owned docs/, decisions, executable code, and tests are the sources of truth. .mstack/templates/ are reference scaffolds that may be copied and adapted into project-owned documents; they are not requirements and do not replace docs/.

Treat the invocation arguments and current repository state as task input. Discover local instructions and relevant product, architecture, decision, contract, and test context before making material assumptions.

Method

  1. Load handoff, tickets, and git state as authoritative over chat memory.
  2. Spot-check verification claims; drop completed work from the plan.
  3. Route to the correct skill or lifecycle prompt for the remaining frontier.
  4. State and begin the first concrete action.

Deliverables

  • Reconstructed status and first action.
  • Corrections where the handoff disagreed with the repository.

Constraints

  • Do not redo completed green checks without cause.
  • Do not invent commits or closed tickets.
  • Do not ignore an explicit pause condition.

Delegation and parallel safety

  • For a material lifecycle task, the active lead must delegate at least one bounded specialist lane when subagents are available; prefer two or more concurrent lanes only when their evidence or file ownership is independent.
  • The active lead owns acceptance criteria and final integration. Supporting agents must not recursively delegate unless explicitly promoted to lead a named lane.
  • Give each delegate distinct inputs, outputs, and ownership. Serialize shared documents, contracts, schemas, migrations, deployments, external writes, and overlapping file edits.
  • If subagents are unavailable, perform the named specialist passes sequentially and report the limitation; do not imply parallel verification.
  • Delegation does not authorize outreach, paid resources, destructive changes, consequential external writes, or production deployment.

Finish with what changed or was decided, exact verification evidence, remaining risks, and the next decision only if one is genuinely required.

User arguments: $ARGUMENTS